Hello, friend.

Lucy Li

As a rising senior at Stanford University, I'm studying artificial intelligence as well as human minds, behavior, and language. I'm mainly interested in natural language processing, but also exploring related fields.

I'm very involved with the Symbolic Systems Program as a board member of the student society. I enjoy reading, writing, boba, indoor gardening, and photography. I'm also passionate about education, especially when it comes to increasing diversity in science, technology, engineering, and math (STEM).

Last winter, I spent a quarter at Oxford University, where I studied theoretical neuroscience. I'm currently a research assistant with the Stanford Network Analysis Project.

Wishlist: cool data visualizations, book recommendations, cat papers, and enthusiastic students who want to take EE 103 next fall.

Languages: Python, Java, C, C++, English, Mandarin, and French.


I publish under the name L. Lucy. (The title for this section is misleading because I have only one paper right now... I'm working on fixing this, I promise.)

Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning.

Distributional word embeddings such as GloVe and word2vec are widely used in NLP, but they may be deficient for predicting some types of meaning. We used semantic norm datasets to evaluate these representations. Link.


Here are some of my course projects:

Historical and Modern Image-to-Image Translation with Generative Adversarial Networks

Since everyone is doing GANs stuff these days... we used CycleGANs to colorize historical images and yield some okay-looking results. Link.

The Effect of Speech Disfluencies on Turn-Taking

We predicted end-of-turns in spoken conversations using filler words and discourse markers. Link.

A Resource Rational Analysis of Memory Use in Bayesian Updating

If noise-less memories are costly, how should one update one’s beliefs when given new observations? We built a hierarchical Bayesian model of memory, as part of Noah Goodman's class on computation and cognition (CS428/Psych204). Link.

DominAI: An AI Player for Dominoes

We created an agent using game playing and sampling algorithms to beat opponents at four-player dominoes. Link.